# trustshell

> trustshell — william2333zz-trustshell. Use this tool when you need to ensure AI agent security and identify vulnerabilities through autonomous attacks and static analysis. It solves problems related to AI security testing and validation, providing a comprehensive toolkit for exploit validation and red-team exercises. The trustshell toolkit takes in AI agent configurations and outputs vulnerability reports and exploit validation results.

Canonical page: https://skillsregistry.net/skills/william2333zz-trustshell  
JSON: https://api.skillsregistry.net/v1/skills/william2333zz-trustshell

## Description

Open-source toolkit for AI agent security — autonomous attacker + static engine + scanner + red-team skills. Exploit-validated. trust-shell.com

## Trust

- **Trust score (0–1):** 0.85
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/William2333ZZ/trustshell)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "william2333zz-trustshell"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/william2333zz-trustshell` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/william2333zz-trustshell/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt